Day #28 - R - Forecast Library Examples

Following Examples discussed. Library used - R - Forecast Library

• Moving Average
• Single Exponential Smoothing - Uses single smoothing factor
• Double Exponential Smoothing - Uses two constants and is better at handling trends
• Triple Exponential Smoothing - Smoothing factor, trend, seasonal factors considered
• ARIMA

	#Create Dataset
	#Generate sample data of 100 records with mean = 850 and standard deviation = 900
	myvector <- rnorm(1000, 850, 900)
	myvector
	#Split it into timeseries weekly data for 104 weeks
	myts = ts(myvector, start=c(2014,1),end=c(2016,1),frequency=104)
	myts
	#Plot Data
	plot(myts)
	#Apply moving average
	sm = ma(myts, order=4)#4 week average
	plot(sm)
	#Plotting with Single Exponential
	fit = HoltWinters(myts,beta = FALSE, gamma = FALSE)
	plot(fit)
	#Plotting with Double Exponential
	fit = HoltWinters(myts, gamma = FALSE)
	plot(fit)
	#triple exponential
	fit = HoltWinters(myts)
	#Additive triple exponential
	fit1 = HoltWinters(myts, seasonal = "multiplicative")
	#Multiplicative triple exponential
	fit2 = HoltWinters(myts, seasonal = "additive")
	#ARIMA
	arimafit = arima(myts, order = c(0,0,0))
	summary(arimafit)
	plot(myts, xlim=c(2014,2016),lw=2,col="blue")
	lines(predict(arimafit,n.ahead=50)$pred,lw=2,col="red")
	#Auto Regression
	arfit = ar(myts)
	summary(arfit)
	pred = predict(arfit,n.ahead=30)
	plot(myts,type="l",xlim=c(2014,2016),ylim=c(100,2200),xlab="weeks",ylab="forecast")
	lines(pred$pred,col="red")

view raw RForecastExample.R hosted with ❤ by GitHub

Happy Learning!!!